Next Article in Journal
Quantifying the Training and Match-Play External and Internal Load of Elite Gaelic Football Players
Next Article in Special Issue
Spider U-Net: Incorporating Inter-Slice Connectivity Using LSTM for 3D Blood Vessel Segmentation
Previous Article in Journal
Baseline Subsoil CO2 Gas Measurements and Micrometeorological Monitoring: Above Canopy Turbulence Effects on the Subsoil CO2 Dynamics in Temperate Deciduous Forest
Previous Article in Special Issue
Synthesize and Segment: Towards Improved Catheter Segmentation via Adversarial Augmentation
Open AccessArticle

Fully Leveraging Deep Learning Methods for Constructing Retinal Fundus Photomontages

1
Department of Ophthalmology, Seoul National University College of Medicine, Seoul National University Bundang Hospital, Seongnam 13620, Korea
2
School of Electrical Engineering, Kookmin University, Seoul 02707, Korea
*
Authors to whom correspondence should be addressed.
Current address: StradVision, Inc. 505, 464, Gangnam-daero, Gangnam-gu, Seoul 06123, Korea.
Academic Editor: Francesco Bianconi
Appl. Sci. 2021, 11(4), 1754; https://doi.org/10.3390/app11041754
Received: 13 January 2021 / Revised: 10 February 2021 / Accepted: 11 February 2021 / Published: 16 February 2021
Retinal photomontages, which are constructed by aligning and integrating multiple fundus images, are useful in diagnosing retinal diseases affecting peripheral retina. We present a novel framework for constructing retinal photomontages that fully leverage recent deep learning methods. Deep learning based object detection is used to define the order of image registration and blending. Deep learning based vessel segmentation is used to enhance image texture to improve registration performance within a two step image registration framework comprising rigid and non-rigid registration. Experimental evaluation demonstrates the robustness of our montage construction method with an increased amount of successfully integrated images as well as reduction of image artifacts. View Full-Text
Keywords: fundus photo; montage; object detection; keypoint matching; vessel segmentation; rigid registration; non rigid registration; blending fundus photo; montage; object detection; keypoint matching; vessel segmentation; rigid registration; non rigid registration; blending
Show Figures

Figure 1

MDPI and ACS Style

Kim, J.; Go, S.; Noh, K.; Park, S.; Lee, S. Fully Leveraging Deep Learning Methods for Constructing Retinal Fundus Photomontages. Appl. Sci. 2021, 11, 1754. https://doi.org/10.3390/app11041754

AMA Style

Kim J, Go S, Noh K, Park S, Lee S. Fully Leveraging Deep Learning Methods for Constructing Retinal Fundus Photomontages. Applied Sciences. 2021; 11(4):1754. https://doi.org/10.3390/app11041754

Chicago/Turabian Style

Kim, Jooyoung; Go, Sojung; Noh, Kyoungjin; Park, Sangjun; Lee, Soochahn. 2021. "Fully Leveraging Deep Learning Methods for Constructing Retinal Fundus Photomontages" Appl. Sci. 11, no. 4: 1754. https://doi.org/10.3390/app11041754

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop